本文整理汇总了Python中Helper.getDomainsFromTsv方法的典型用法代码示例。如果您正苦于以下问题:Python Helper.getDomainsFromTsv方法的具体用法?Python Helper.getDomainsFromTsv怎么用?Python Helper.getDomainsFromTsv使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类Helper
的用法示例。
在下文中一共展示了Helper.getDomainsFromTsv方法的2个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: initGeneLevelProteins
# 需要导入模块: import Helper [as 别名]
# 或者: from Helper import getDomainsFromTsv [as 别名]
def initGeneLevelProteins(filename, tsvfileA, tsvfileB, useDomains):
proteinsA = {}
proteinsB = {}
orthologGroups = {}
groupsStarted = False
rcp = ConfigParser.RawConfigParser()
rcp.read("orthology.cfg")
cutoff = rcp.getint("Options", "domainlengthcutoff")
if useDomains:
domainsA, shortA = Helper.getDomainsFromTsv(tsvfileA, cutoff)
domainsB, shortB = Helper.getDomainsFromTsv(tsvfileB, cutoff)
handle = open(filename, "r")
ort = None
lineStarts = ["Group", "Score", "Boots", "_____"]
for line in handle.readlines():
if groupsStarted:
if line[0:5] not in lineStarts:
hasA = not line.startswith(" ")
temp = []
splittedLine = line.split()
temp = ort.getBasicProteins(splittedLine)
if hasA:
temp[0].__class__ = GeneLevelProtein
proteinsA[temp[0].accession] = temp[0]
if useDomains:
temp[0].domains = domainsA[temp[0].accession]
score = float(splittedLine[1].split("%")[0])
ort.inparalogsA[temp[0].accession] = score
if not hasA or len(temp) > 1:
temp[-1].__class__ = GeneLevelProtein
proteinsB[temp[-1].accession] = temp[-1]
if useDomains:
temp[-1].domains = domainsB[temp[-1].accession]
score = float(splittedLine[-1].split("%")[0])
ort.inparalogsB[temp[-1].accession] = score
elif line.startswith("Group"):
ort = OrthologyGroup.getBasicOrthologyGroup(line, True, orthologGroups)
elif line.startswith("Bootstrap"):
ort.addSeeds(line)
else:
if line.startswith("_"):
groupsStarted = True
pairsCount = 0
for g in orthologGroups:
pairsCount += len(orthologGroups[g].inparalogsA) * len(orthologGroups[g].inparalogsB)
print pairsCount, "should be the amount of pairs"
print len(orthologGroups), "ortholog groups read from the file"
handle.close()
if useDomains:
return proteinsA, proteinsB, orthologGroups, shortA, shortB
else:
return proteinsA, proteinsB, orthologGroups
示例2: in
# 需要导入模块: import Helper [as 别名]
# 或者: from Helper import getDomainsFromTsv [as 别名]
if opt in ("-t", "--tsvfile"):
tsvfile = arg
elif opt in ("-o", "--ofile"):
outputfile = arg
elif opt in ("-p", "--proteomefile"):
proteomefile = arg
else:
ok = False
if ok:
tsvpath = rcp.get("Filepaths", "tsvpath")
outpath = rcp.get("Filepaths", "retrieveddomainspath")
cutoff = rcp.getint("Options", "domainlengthcutoff")
idlistpath = rcp.get("Filepaths", "idlistpath")
idlistsuffix = rcp.get("Fileendings", "idlistsuffix")
domains, short = Helper.getDomainsFromTsv(tsvpath+tsvfile, cutoff)
output = getDomainsForSequences(domains, idlistpath+proteomefile + idlistsuffix)
outFile = open(outpath+outputfile, 'w')
outFile.write(str(output))
outFile.close()
else:
print __doc__
sys.exit(0)
def getDomainsForSequences(domains, proteomefile):
handle = open(proteomefile, "rU")
result = ''
accessions = []
for record in handle.readlines():
accessions.append(record.split('\n')[0])